Bridging control and artificial intelligence theories for diagnosis: A survey

Travé-Massuyès, Louise

doi:10.1016/j.engappai.2013.09.018

Cited by 51 publications

(44 citation statements)

References 97 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hypothesis testing combining model-based FDI with statistical change detection and testing with methods from artificial intelligence could be employed to avoid nuisance alarms on-board. Such methods were covered in the survey by [31] and a study of data driven diagnosis showed design for isolability of different types of faults in automotive engines [32]. The same authors suggested an explicit comparison of the probability distribution of the residual, estimated online using current data, with no-fault residual distributions in [33] and found that tiny faults, i.e.…”

Section: Detection Behaviour For Incipient Faultsmentioning

confidence: 99%

Mooring system diagnosis and structural reliability control for position moored vessels

Fang

Blanke

Leira

2015

Control Engineering Practice

View full text Add to dashboard Cite

Early diagnosis and fault-tolerant control are essential for safe operation of floating platforms where mooring systems maintain vessel position and must withstand environmental loads. This paper considers two critical faults, line breakage and loss of a buoyancy element and employs vector statistical change detection for timely diagnosis of faults. Diagnosis design is scrutinized and a procedure is proposed based on specified false alarm probability and estimation of the distribution of the test statistics on which change detection is based. A structural reliability index is applied for monitoring the safety level of each mooring line and, a set-point chasing algorithm accommodates the effects of line failure, as an integral part of the reliabilitybased set-point chasing control algorithm. The feasibility of the diagnosis and of the fault-tolerant control strategy is verified in model basin tests.

show abstract

Section: Detection Behaviour For Incipient Faultsmentioning

confidence: 99%

Mooring system diagnosis and structural reliability control for position moored vessels

Fang

Blanke

Leira

2015

Control Engineering Practice

View full text Add to dashboard Cite

show abstract

“…where the state vector x(t), the input vector u(t), and the output vector y(t) are vectors of continuous variables, and the behavioral model f and the observation model g are functions of the input and state vectors [136]. As many laws of physics are DAE:s, this type of model can with high precision capture the behavior of dynamic mechanical, hydraulic, and electrical systems.…”

Section: Fault Detection and Isolationmentioning

confidence: 99%

“…For thorough reviews of the FDI approach, see e.g. [22,64,136,137]. A typical FDI model describes the nominal behavior of the system using a state space model of differential algebraic equations (DAE:s):…”

Section: Fault Detection and Isolationmentioning

confidence: 99%

Troubleshooting Trucks: Automated Planning and Diagnosis

Warnquist¹

2015

View full text Add to dashboard Cite

This thesis considers computer-assisted troubleshooting of heavy vehicles such as trucks and buses. In this setting, the person that is troubleshooting a vehicle problem is assisted by a computer that is capable of listing possible faults that can explain the problem and gives recommendations of which actions to take in order to solve the problem such that the expected cost of restoring the vehicle is low. To achieve this, such a system must be capable of solving two problems: the diagnosis problem of finding which the possible faults are and the decision problem of deciding which action should be taken.The diagnosis problem has been approached using Bayesian network models. Frameworks have been developed for the case when the vehicle is in the workshop only and for remote diagnosis when the vehicle is monitored during longer periods of time.The decision problem has been solved by creating planners that select actions such that the expected cost of repairing the vehicle is minimized. New methods, algorithms, and models have been developed for improving the performance of the planner.The theory developed has been evaluated on models of an auxiliary braking system, a fuel injection system, and an engine temperature control and monitoring system.This work has been supported Scania CV AB and FFI -Fordonsstrategisk Forskning och Innovation. iii iv AcknowledgmentsDenna avhandling är slutet på en lång och spännande resa som inte hade varit möjligt utan hjälp. Arbetet med avhandlingen har varit en del av ett forskningssamarbete mellan fordonstillverkaren Scania och institutionen för datavetenskap vid Linköpings universitet.I Linköping vill jag tacka mina handledare Professor Patrick Doherty och Dr Jonas Kvarnström. Patrick har gett mig god träning i och verktyg för hur jag muntligt presenterar min forskning. Jonas har varit ett otroligt stöd vid framtagandet av nya forskningsidéer och forskningsartiklar. Med nästan övermänsklig noggrannhet kan hans skarpa ögon upptäcka minsta oklarhet i snåriga ekvationer. Jag är tacksam för all kunskap han delat med sig av. Jag har lärt mig mycket om hur man skriver vetenskapliga artiklar. Stort tack till Anne Moe, koordinator för doktorander på institutionen för datavetenskap. Hon är en klippa och har gett mig ovärderlig hjälp i den praktiska planeringen av framläggningarna av denna avhandling. Jag vill även tacka alla doktorander på KPLAB för alla spännande lunchdiskussioner.På Scania vill jag först och främst tacka Dr Mattias Nyberg som varit initiativtagare till forskningsprojekten och som gett mig förstklassig handledning. Mattias har tillsammans med Dr Jonas Biteus varit med och utvecklat tillämpningen av min forskning på Scania. Jag vill även tacka alla andra idésprutor som bidragit, i synnerhet Hans Ivendal, Dr Tony Lindgren, Dr Martin Eineborg och övriga i min v arbetsgrupp på Scania. Jag vill även tacka min styrgrupp och alla de skickliga chefer stöttat mig under denna tid: Göran Johansson, Thor Brenden, Per Karlsson, Anna Pernestål, Björn Bertmar och Erik Malmkvist.D...

show abstract

“…Within the field of artificial intelligence, model-based diagnosis, sometimes denoted DX, focuses more on fault isolation and the use of logics to identify faulty behavior, see for example (Reiter, 1987), (de Kleer and Williams, 1987), (Feldman andvan Gemund, 2006), and(de Kleer, 2011). A number of papers compare the different approaches from FDI and DX to bridge and integrate methods from the two fields (Cordier et al, 2004;Travé-Massuyès, 2014). In this thesis, diagnosis systems are considered where fault detection is mainly performed using methods from the FDI community and fault isolation is performed using methods from the DX community, see for example (Cordier et al, 2004).…”

Section: Model-based Diagnosismentioning

confidence: 99%

Diagnosability performance analysis of models and fault detectors

Jung

2015

Linköping Studies in Science and Technology. Dissertations

View full text Add to dashboard Cite

The cover: Graphical illustration of the proposed quantitative fault detectability and isolability performance measure, called distinguishability (Di,j(θ)). Typeset with L A T E X 2εPrinted by LiU-Tryck, Linköping, Sweden 2015 To Ylva i Abstract Model-based diagnosis compares observations from a system with predictions using a mathematical model to detect and isolate faulty components. Analyzing which faults that can be detected and isolated given the model gives useful information when designing a diagnosis system. This information can be used, for example, to determine which residual generators can be generated or to select a sufficient set of sensors that can be used to detect and isolate the faults. With more information about the system taken into consideration during such an analysis, more accurate estimations can be computed of how good fault detectability and isolability that can be achieved.Model uncertainties and measurement noise are the main reasons for reduced fault detection and isolation performance and can make it difficult to design a diagnosis system that fulfills given performance requirements. By taking information about different uncertainties into consideration early in the development process of a diagnosis system, it is possible to predict how good performance can be achieved by a diagnosis system and avoid bad design choices. This thesis deals with quantitative analysis of fault detectability and isolability performance when taking model uncertainties and measurement noise into consideration. The goal is to analyze fault detectability and isolability performance given a mathematical model of the monitored system before a diagnosis system is developed.A quantitative measure of fault detectability and isolability performance for a given model, called distinguishability, is proposed based on the Kullback-Leibler divergence. The distinguishability measure answers questions like "How difficult is it to isolate a fault f i from another fault f j ?". Different properties of the distinguishability measure are analyzed. It is shown for example, that for linear descriptor models with Gaussian noise, distinguishability gives an upper limit for the fault to noise ratio of any linear residual generator. The proposed measure is used for quantitative analysis of a nonlinear mean value model of gas flows in a heavy-duty diesel engine to analyze how fault diagnosability performance varies for different operating points. It is also used to formulate the sensor selection problem, i.e., to find a cheapest set of available sensors that should be used in a system to achieve required fault diagnosability performance.As a case study, quantitative fault diagnosability analysis is used during the design of an engine misfire detection algorithm based on the crankshaft angular velocity measured at the flywheel. Decisions during the development of the misfire detection algorithm are motivated using quantitative analysis of the misfire detectability performance showing, for example, varying detection performance a...

show abstract

Bridging control and artificial intelligence theories for diagnosis: A survey

Cited by 51 publications

References 97 publications

Mooring system diagnosis and structural reliability control for position moored vessels

Mooring system diagnosis and structural reliability control for position moored vessels

Troubleshooting Trucks: Automated Planning and Diagnosis

Diagnosability performance analysis of models and fault detectors

Contact Info

Product

Resources

About